End of training

README.md

@@ -3,6 +3,9 @@ library_name: transformers
 license: cc-by-nc-4.0
 base_model: facebook/mms-1b-all
 tags:
+- automatic-speech-recognition
+- swagen
+- mms
 - generated_from_trainer
 model-index:
 - name: mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
@@ -14,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
 
-This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the SWAGEN - DAT dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6629
-- Cer: 0.1582
+- Loss: 0.5567
+- Cer: 0.1128
 
 ## Model description
 

adapter.dat.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a9f1841c9478d386e19c693a5335f2f981cde39671d75fe978922fc2e29a1a
+size 8819028

all_results.json

@@ -1,15 +1,16 @@
 {
-    "epoch": 15.0,
-    "eval_cer": 0.08226613138358714,
-    "eval_loss": 0.4168073236942291,
-    "eval_runtime": 43.4947,
+    "epoch": 9.845849802371541,
+    "eval_cer": 0.11281315181555161,
+    "eval_loss": 0.5567455887794495,
+    "eval_runtime": 44.5427,
     "eval_samples": 693,
-    "eval_samples_per_second": 15.933,
-    "eval_steps_per_second": 4.0,
-    "total_flos": 1.844747726932012e+19,
-    "train_loss": 0.6772966920547285,
-    "train_runtime": 2708.4445,
+    "eval_samples_per_second": 15.558,
+    "eval_steps_per_second": 3.906,
+    "lambda_grl": 0.9952304067043316,
+    "total_flos": 1.2130383128358582e+19,
+    "train_loss": 0.6886797119140625,
+    "train_runtime": 1822.0691,
     "train_samples": 2020,
-    "train_samples_per_second": 11.187,
-    "train_steps_per_second": 0.703
+    "train_samples_per_second": 16.629,
+    "train_steps_per_second": 1.046
 }

eval_results.json

@@ -1,9 +1,10 @@
 {
-    "epoch": 15.0,
-    "eval_cer": 0.08226613138358714,
-    "eval_loss": 0.4168073236942291,
-    "eval_runtime": 43.4947,
+    "epoch": 9.845849802371541,
+    "eval_cer": 0.11281315181555161,
+    "eval_loss": 0.5567455887794495,
+    "eval_runtime": 44.5427,
     "eval_samples": 693,
-    "eval_samples_per_second": 15.933,
-    "eval_steps_per_second": 4.0
+    "eval_samples_per_second": 15.558,
+    "eval_steps_per_second": 3.906,
+    "lambda_grl": 0.9952304067043316
 }

train_results.json

@@ -1,9 +1,10 @@
 {
-    "epoch": 15.0,
-    "total_flos": 1.844747726932012e+19,
-    "train_loss": 0.6772966920547285,
-    "train_runtime": 2708.4445,
+    "epoch": 9.845849802371541,
+    "lambda_grl": 0.9952304067043316,
+    "total_flos": 1.2130383128358582e+19,
+    "train_loss": 0.6886797119140625,
+    "train_runtime": 1822.0691,
     "train_samples": 2020,
-    "train_samples_per_second": 11.187,
-    "train_steps_per_second": 0.703
+    "train_samples_per_second": 16.629,
+    "train_steps_per_second": 1.046
 }